{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:GRVXGMC4A3ABR4EMH6E3GMTBZD","short_pith_number":"pith:GRVXGMC4","schema_version":"1.0","canonical_sha256":"346b73305c06c018f08c3f89b33261c8e56fa89faef90732f5bc0b622ad1e41a","source":{"kind":"arxiv","id":"1506.01698","version":1},"attestation_state":"computed","paper":{"title":"The Long-Short Story of Movie Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Bernt Schiele, Marcus Rohrbach","submitted_at":"2015-06-04T19:45:36Z","abstract_excerpt":"Generating descriptions for videos has many applications including assisting blind people and human-robot interaction. The recent advances in image captioning as well as the release of large-scale movie description datasets such as MPII Movie Description allow to study this task in more depth. Many of the proposed methods for image captioning rely on pre-trained object classifier CNNs and Long-Short Term Memory recurrent networks (LSTMs) for generating descriptions. While image description focuses on objects, we argue that it is important to distinguish verbs, objects, and places in the challe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1506.01698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-04T19:45:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc3d1f0148e054c5e1cc8a117c4c9f31a85ec380225173f6ad7266a3ec5d6b7b","abstract_canon_sha256":"229235e6b2d9fb06eafd67fec71c49fbd7d8efc1e3c9f2f8f6540f91c974bda9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:57:18.201292Z","signature_b64":"s6CMU/SrDwsrmMzulnGmrxKSM8Fx7B12znNU5GuEftsmQUlu6Rn+MxRtT17Tu1G+RwqggPoSPeOfF7WKjp1HCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"346b73305c06c018f08c3f89b33261c8e56fa89faef90732f5bc0b622ad1e41a","last_reissued_at":"2026-05-18T01:57:18.200859Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:57:18.200859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Long-Short Story of Movie Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Bernt Schiele, Marcus Rohrbach","submitted_at":"2015-06-04T19:45:36Z","abstract_excerpt":"Generating descriptions for videos has many applications including assisting blind people and human-robot interaction. The recent advances in image captioning as well as the release of large-scale movie description datasets such as MPII Movie Description allow to study this task in more depth. Many of the proposed methods for image captioning rely on pre-trained object classifier CNNs and Long-Short Term Memory recurrent networks (LSTMs) for generating descriptions. While image description focuses on objects, we argue that it is important to distinguish verbs, objects, and places in the challe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01698","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1506.01698","created_at":"2026-05-18T01:57:18.200924+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.01698v1","created_at":"2026-05-18T01:57:18.200924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01698","created_at":"2026-05-18T01:57:18.200924+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRVXGMC4A3AB","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRVXGMC4A3ABR4EM","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRVXGMC4","created_at":"2026-05-18T12:29:22.688609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GRVXGMC4A3ABR4EMH6E3GMTBZD","json":"https://pith.science/pith/GRVXGMC4A3ABR4EMH6E3GMTBZD.json","graph_json":"https://pith.science/api/pith-number/GRVXGMC4A3ABR4EMH6E3GMTBZD/graph.json","events_json":"https://pith.science/api/pith-number/GRVXGMC4A3ABR4EMH6E3GMTBZD/events.json","paper":"https://pith.science/paper/GRVXGMC4"},"agent_actions":{"view_html":"https://pith.science/pith/GRVXGMC4A3ABR4EMH6E3GMTBZD","download_json":"https://pith.science/pith/GRVXGMC4A3ABR4EMH6E3GMTBZD.json","view_paper":"https://pith.science/paper/GRVXGMC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.01698&json=true","fetch_graph":"https://pith.science/api/pith-number/GRVXGMC4A3ABR4EMH6E3GMTBZD/graph.json","fetch_events":"https://pith.science/api/pith-number/GRVXGMC4A3ABR4EMH6E3GMTBZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRVXGMC4A3ABR4EMH6E3GMTBZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRVXGMC4A3ABR4EMH6E3GMTBZD/action/storage_attestation","attest_author":"https://pith.science/pith/GRVXGMC4A3ABR4EMH6E3GMTBZD/action/author_attestation","sign_citation":"https://pith.science/pith/GRVXGMC4A3ABR4EMH6E3GMTBZD/action/citation_signature","submit_replication":"https://pith.science/pith/GRVXGMC4A3ABR4EMH6E3GMTBZD/action/replication_record"}},"created_at":"2026-05-18T01:57:18.200924+00:00","updated_at":"2026-05-18T01:57:18.200924+00:00"}